@svpino: MCP is not dead. For the people who keep saying "bUt McP pUts GaRbaGe iN yOuR cOntExT", that's an outdated complaint: N…
Summary
A defense of MCP (Model Context Protocol) against criticism that it puts garbage in context, noting that modern tools like Claude Code, Codex, and Cursor implement progressive disclosure and load MCP tools on demand, making the complaint outdated. The author argues MCP is best for cloud-hosted platforms requiring authentication and discoverability.
Similar Articles
MCP is dead?
A technical critique of the Model Context Protocol (MCP) arguing that it consumes excessive context window tokens, has low operational reliability, and overlaps with existing CLI/API approaches, with measurements from Quandri's stack showing 10.5% context usage.
@RhysSullivan: https://x.com/RhysSullivan/status/2070311929038680262
The author reflects on why the Model Context Protocol (MCP) has struggled, contrasting it with CLI-based agent workflows and arguing for more flexible tool integration. They suggest that agents should support MCP, CLI, API, etc., and express optimism about MCP's future despite current challenges.
Most MCP servers don't need to exist. Your case might be an exception
Most MCP servers are unnecessary; this article presents a framework for deciding when an MCP server is warranted, emphasizing the need for stable APIs and CLIs first.
Introducing the MDN MCP server
Mozilla announced the MDN MCP server, which uses the Model Context Protocol to provide AI coding tools with up-to-date MDN documentation and browser compatibility data, enabling more accurate web platform information in development workflows.
@akshay_pachaar: The MCP vs CLI debate. For most of 2025, AI Engineers argued about it. The skeptics had real numbers: - Playwright MCP …
Anthropic's 'Code Mode' reframes the MCP vs CLI debate by having AI agents write code to call tools via a runtime rather than loading full schemas into context, drastically reducing token usage. This approach combines MCP's typed contracts with lazy loading, proving the protocol is evolving rather than dying.